Variational Continual Learning
This addresses the problem of catastrophic forgetting for AI systems that need to learn continuously over time, representing a novel method for a known bottleneck.
The paper tackled catastrophic forgetting in continual learning by introducing Variational Continual Learning (VCL), which fuses online variational inference with Monte Carlo methods, and it outperformed state-of-the-art methods on various tasks.
This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The framework can successfully train both deep discriminative models and deep generative models in complex continual learning settings where existing tasks evolve over time and entirely new tasks emerge. Experimental results show that VCL outperforms state-of-the-art continual learning methods on a variety of tasks, avoiding catastrophic forgetting in a fully automatic way.